© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48418
    Prev
    Next
    INDEX
    Explanations

    . followed by 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enu
    -0.08
    iad
    -0.08
    ürzt
    -0.07
    æī«æııäºĮç»´çłģä¸ĭè½½
    -0.07
    NSData
    -0.07
    urnished
    -0.07
    æĭĽèģĺåħ¬åijĬ
    -0.07
    onge
    -0.07
    ("~/
    -0.07
    Invoker
    -0.07
    POSITIVE LOGITS
    åħĭæŀĹ
    0.08
    妻
    0.08
    度é«ĺ
    0.07
    oppi
    0.07
    кÑĢи
    0.07
     íķĺëĤĺ
    0.06
    好äºĨ
    0.06
    lement
    0.06
    à°¥
    0.06
    olie
    0.06
    Activations Density 0.005%

    No Known Activations